udbnn 0.0.3

Experiment to determine whetever a large batch-size can be helpful with extremely umbalanced datasets.

Experiment to determine whetever a large batch-size can be helpful with extremely umbalanced datasets.

How do I get this?

Just run:

pip install tensorflow # or tensorflow-gpu, whetever you have a gpu or not
git clone https://github.com/LucaCappelletti94/udbnn.git
cd udbnn
pip install .

How do I run the experiments?

Since the experiments take quite a bit to run, I suggest you to run them while in a TMUX-like environment. If available, you should consider using a computer with a tensorflow-compatible GPU.

Then just run with a python shell:

from udbnn import run
run("dataset")